Measuring Bias in Contextualized Word Representations

18 June 2019

Papers citing "Measuring Bias in Contextualized Word Representations"

50 / 272 papers shown

Title
SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets Ann Yuan Daphne Ippolito Vitaly Nikolaev Chris Callison-Burch Andy Coenen Sebastian Gehrmann SyDa 104 20 0 11 Nov 2021
NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM Connor Holmes Minjia Zhang Yuxiong He Bo Wu 21 18 0 28 Oct 2021
Post-processing for Individual Fairness Felix Petersen Debarghya Mukherjee Yuekai Sun Mikhail Yurochkin FaML 14 80 0 26 Oct 2021
LMSOC: An Approach for Socially Sensitive Pretraining Vivek Kulkarni Shubhanshu Mishra A. Haghighi 12 13 0 20 Oct 2021
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models Nicholas Meade Elinor Poole-Dayan Siva Reddy 16 123 0 16 Oct 2021
Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting Zahra Fatemi Chen Xing Wenhao Liu Caiming Xiong CLL 17 34 0 11 Oct 2021
On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias Ting-Rui Chiang 22 3 0 11 Oct 2021
An Empirical Investigation of Learning from Biased Toxicity Labels Neel Nanda J. Uesato Sven Gowal 10 0 0 04 Oct 2021
Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models Robert Wolfe Aylin Caliskan 85 51 0 01 Oct 2021
Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens Saad Hassan Matt Huenerfauth Cecilia Ovesdotter Alm 38 38 0 01 Oct 2021
Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you? Rochelle Choenni Ekaterina Shutova R. Rooij 80 29 0 21 Sep 2021
Simple Entity-Centric Questions Challenge Dense Retrievers Christopher Sciavolino Zexuan Zhong Jinhyuk Lee Danqi Chen RALM 11 159 0 17 Sep 2021
Mitigating Language-Dependent Ethnic Bias in BERT Jaimeen Ahn Alice H. Oh 131 91 0 13 Sep 2021
Sustainable Modular Debiasing of Language Models Anne Lauscher Tobias Lüken Goran Glavas 47 120 0 08 Sep 2021
Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models Eric Michael Smith Adina Williams 22 28 0 07 Sep 2021
Diachronic Analysis of German Parliamentary Proceedings: Ideological Shifts through the Lens of Political Biases Tobias Walter Celina Kirschner Steffen Eger Goran Glavavs Anne Lauscher Simone Paolo Ponzetto 6 20 0 13 Aug 2021
Sexism in the Judiciary Noa Baker Gillis FaML 8 2 0 29 Jun 2021
Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics Paula Czarnowska Yogarshi Vyas Kashif Shah 18 104 0 28 Jun 2021
Towards Understanding and Mitigating Social Biases in Language Models Paul Pu Liang Chiyu Wu Louis-Philippe Morency Ruslan Salakhutdinov 25 378 0 24 Jun 2021
A Survey of Race, Racism, and Anti-Racism in NLP Anjalie Field Su Lin Blodgett Zeerak Talat Yulia Tsvetkov 21 122 0 21 Jun 2021
Evaluating Gender Bias in Hindi-English Machine Translation Gauri Gupta Krithika Ramesh Sanjay Singh 11 22 0 16 Jun 2021
Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning Piotr Pikekos Henryk Michalewski Mateusz Malinowski 22 28 0 07 Jun 2021
Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Model Kathleen C. Fraser I. Nejadgholi S. Kiritchenko 11 37 0 04 Jun 2021
Towards Equal Gender Representation in the Annotations of Toxic Language Detection Elizabeth Excell Noura Al Moubayed 9 14 0 04 Jun 2021
How to Adapt Your Pretrained Multilingual Model to 1600 Languages Abteen Ebrahimi Katharina Kann LRM VLM 22 67 0 03 Jun 2021
Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models Tejas Srinivasan Yonatan Bisk VLM 16 55 0 18 Apr 2021
Unmasking the Mask -- Evaluating Social Biases in Masked Language Models Masahiro Kaneko Danushka Bollegala 13 70 0 15 Apr 2021
NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media Grace Luo Trevor Darrell Anna Rohrbach 6 84 0 13 Apr 2021
Low-Complexity Probing via Finding Subnetworks Steven Cao Victor Sanh Alexander M. Rush 11 51 0 08 Apr 2021
Self-Supervised Test-Time Learning for Reading Comprehension Pratyay Banerjee Tejas Gokhale Chitta Baral SSL 15 28 0 20 Mar 2021
FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders Pengyu Cheng Weituo Hao Siyang Yuan Shijing Si Lawrence Carin 23 100 0 11 Mar 2021
Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance J. Minot N. Cheney Marc E. Maier Danne C. Elbers C. Danforth P. Dodds FaML 12 3 0 10 Mar 2021
Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do P. Schramowski Cigdem Turan Nico Andersen Constantin Rothkopf Kristian Kersting 25 281 0 08 Mar 2021
Causal Attention for Vision-Language Tasks Xu Yang Hanwang Zhang Guojun Qi Jianfei Cai CML 23 148 0 05 Mar 2021
Biomedical Question Answering: A Survey of Approaches and Challenges Qiao Jin Zheng Yuan Guangzhi Xiong Qian Yu Huaiyuan Ying Chuanqi Tan Mosha Chen Songfang Huang Xiaozhong Liu Sheng Yu 21 95 0 10 Feb 2021
Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models Hannah Rose Kirk Yennie Jun Haider Iqbal Elias Benussi Filippo Volpin F. Dreyer Aleksandar Shtedritski Yuki M. Asano 6 180 0 08 Feb 2021
Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models Daniel de Vassimon Manela D. Errington Thomas Fisher B. V. Breugel Pasquale Minervini 6 88 0 24 Jan 2021
Debiasing Pre-trained Contextualised Embeddings Masahiro Kaneko Danushka Bollegala 210 138 0 23 Jan 2021
Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective S. Kiritchenko I. Nejadgholi Kathleen C. Fraser AILaw 20 83 0 22 Dec 2020
Model Choices Influence Attributive Word Associations: A Semi-supervised Analysis of Static Word Embeddings Geetanjali Bihani Julia Taylor Rayz 11 2 0 14 Dec 2020
Cross-Loss Influence Functions to Explain Deep Network Representations Andrew Silva Rohit Chopra Matthew C. Gombolay TDI 13 15 0 03 Dec 2020
Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis Michael A. Lepori 24 12 0 24 Nov 2020
Situated Data, Situated Systems: A Methodology to Engage with Power Relations in Natural Language Processing Research Lucy Havens Melissa Mhairi Terras Benjamin Bach Beatrice Alex 9 21 0 11 Nov 2020
Semantic coordinates analysis reveals language changes in the AI field Zining Zhu Yang Xu Frank Rudzicz 18 0 0 01 Nov 2020
Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases Ryan Steed Aylin Caliskan SSL 17 156 0 28 Oct 2020
Towards Ethics by Design in Online Abusive Content Detection S. Kiritchenko I. Nejadgholi 13 13 0 28 Oct 2020
Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias Marion Bartl Malvina Nissim Albert Gatt 9 122 0 27 Oct 2020
Discovering and Interpreting Biased Concepts in Online Communities Xavier Ferrer-Aran Tom van Nuenen Natalia Criado Jose Such 9 2 0 27 Oct 2020
On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning Xisen Jin Francesco Barbieri Brendan Kennedy Aida Mostafazadeh Davani Leonardo Neves Xiang Ren 19 5 0 24 Oct 2020
Inferring symmetry in natural language Chelsea Tanchip Lei Yu Aotao Xu Yang Xu 8 5 0 16 Oct 2020